Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 319 969 761 195 455 495 197 456 189 403 417 244 710 882 751 976 198 412 528 185
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 710  NA 976 412 198  NA  NA 185 456 189 495 417 403 319 455 969 882 197 195 244 751 761 528
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 2 2 3 2 1 5 1 2 4 4
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "i" "w" "l" "p" "c" "G" "H" "B" "I" "E"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  2 16
which( manyNumbersWithNA > 900 )
[1]  3 16
which( is.na( manyNumbersWithNA ) )
[1] 2 6 7

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 969 976
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 969 976
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 969 976

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "G" "H" "B" "I" "E"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "i" "w" "l" "p" "c"
manyNumbers %in% 300:600
 [1]  TRUE FALSE FALSE FALSE  TRUE  TRUE FALSE  TRUE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE
[18]  TRUE  TRUE FALSE
which( manyNumbers %in% 300:600 )
[1]  1  5  6  8 10 11 18 19
sum( manyNumbers %in% 300:600 )
[1] 8

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" NA      "large" "small" "small" NA      NA      "small" "small" "small" "small" "small" "small"
[14] "small" "small" "large" "large" "small" "small" "small" "large" "large" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "UNKNOWN" "large"   "small"   "small"   "UNKNOWN" "UNKNOWN" "small"   "small"   "small"  
[11] "small"   "small"   "small"   "small"   "small"   "large"   "large"   "small"   "small"   "small"  
[21] "large"   "large"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 710  NA 976   0   0  NA  NA   0   0   0   0   0   0   0   0 969 882   0   0   0 751 761 528

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 2 3 1 5 4
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  2  3  1  5  4
duplicated( duplicatedNumbers )
 [1] FALSE  TRUE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 3
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 976
which.min( manyNumbersWithNA )
[1] 8
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 185
range( manyNumbersWithNA, na.rm = TRUE )
[1] 185 976

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 710  NA 976 412 198  NA  NA 185 456 189 495 417 403 319 455 969 882 197 195 244 751 761 528
sort( manyNumbersWithNA )
 [1] 185 189 195 197 198 244 319 403 412 417 455 456 495 528 710 751 761 882 969 976
sort( manyNumbersWithNA, na.last = TRUE )
 [1] 185 189 195 197 198 244 319 403 412 417 455 456 495 528 710 751 761 882 969 976  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 976 969 882 761 751 710 528 495 456 455 417 412 403 319 244 198 197 195 189 185  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 710  NA 976 412 198
order( manyNumbersWithNA[1:5] )
[1] 5 4 1 3 2
rank( manyNumbersWithNA[1:5] )
[1] 3 5 4 2 1
sort( mixedLetters )
 [1] "B" "c" "E" "G" "H" "i" "I" "l" "p" "w"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 9.5 7.5 5.0 5.0 5.0 1.0 9.5 2.5 7.5 2.5
rank( manyDuplicates, ties.method = "min" )
 [1] 9 7 4 4 4 1 9 2 7 2
rank( manyDuplicates, ties.method = "random" )
 [1]  9  7  4  5  6  1 10  2  8  3

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000 -0.60526408  0.23053859 -0.22247176
 [9] -1.67008120  2.05712736 -1.25038624  0.37534550  1.43015942 -0.09346186 -1.94085832
round( v, 0 )
 [1] -1  0  0  0  1 -1  0  0 -2  2 -1  0  1  0 -2
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.6  0.2 -0.2 -1.7  2.1 -1.3  0.4  1.4 -0.1 -1.9
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.61  0.23 -0.22 -1.67  2.06 -1.25  0.38  1.43 -0.09 -1.94
floor( v )
 [1] -1 -1  0  0  1 -1  0 -1 -2  2 -2  0  1 -1 -2
ceiling( v )
 [1] -1  0  0  1  1  0  1  0 -1  3 -1  1  2  0 -1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC